{"id":"W2791039059","doi":"10.1007/978-3-319-77553-1_9","title":"Scaling Tangled Program Graphs to Visual Reinforcement Learning in ViZDoom","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Reinforcement learning; Computer science; Task (project management); Artificial intelligence; Frame (networking); Process (computing); Code (set theory); Pixel; Graph; Machine learning; Theoretical computer science; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001807914,0.0008024591,0.0007600332,0.002253384,0.0003757472,0.001165208,0.004029999,0.0004281371,0.00006819616],"category_scores_gemma":[0.0003972614,0.0007939676,0.0001802622,0.001944317,0.0005908401,0.0007252152,0.00282436,0.001564577,0.0002284032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000708014,"about_ca_system_score_gemma":0.0005720743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003393794,"about_ca_topic_score_gemma":0.00005289411,"domain_scores_codex":[0.9934533,0.0000759116,0.001095345,0.002057718,0.001894345,0.001423343],"domain_scores_gemma":[0.9969941,0.0004667716,0.0004743441,0.001331208,0.0003742391,0.0003593373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008814852,0.0000212009,0.0001453546,0.00002869532,0.000009050403,0.00005842818,0.00137506,0.760992,0.00005238498,0.002905182,0.00001333637,0.2343905],"study_design_scores_gemma":[0.0003989998,0.001187991,0.000123561,0.0008740992,0.000006906264,0.00002294433,8.773447e-7,0.9832054,0.0004595115,0.009454544,0.003327713,0.0009374351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005270123,0.00006857871,0.9916686,0.00033286,0.001651131,0.001303279,2.825097e-7,0.0005149077,0.003933328],"genre_scores_gemma":[0.3754551,0.0000322895,0.6200158,0.001924155,0.0005638122,0.00007292929,0.00001352391,0.000100646,0.001821696],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3749281,"threshold_uncertainty_score":0.9998717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01606880271556596,"score_gpt":0.2794028763550346,"score_spread":0.2633340736394687,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}